Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Related tags

Deep LearningPASF
Overview

Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Beining Han,   Chongyi Zheng,   Harris Chan,   Keiran Paster,   Michael R. Zhang,   Jimmy Ba

paper

Summary: Deep Reinforcement Learning agents often face unanticipated environmental changes after deployment in the real world. These changes are often spurious and unrelated to the underlying problem, such as background shifts for visual input agents. Unfortunately, deep RL policies are usually sensitive to these changes and fail to act robustly against them. This resembles the problem of domain generalization in supervised learning. In this work, we study this problem for goal-conditioned RL agents. We propose a theoretical framework in the Block MDP setting that characterizes the generalizability of goal-conditioned policies to new environments. Under this framework, we develop a practical method PA-SkewFit (PASF) that enhances domain generalization.

@article{han2021learning,
  title={Learning Domain Invariant Representations in Goal-conditioned Block MDPs},
  author={Han, Beining and Zheng, Chongyi and Chan, Harris and Paster, Keiran and Zhang, Michael and Ba, Jimmy},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  year={2021}
}

Installation

Our code was adapted from rlkit and was tested on a Ubuntu 20.04 server.

This instruction assumes that you have already installed NVIDIA driver, Anaconda, and MuJoCo.

You'll need to get your own MuJoCo key if you want to use MuJoCo.

1. Create Anaconda environment

Install the included Anaconda environment

$ conda env create -f environment/pasf_env.yml
$ source activate pasf_env
(pasf_env) $ python

2. Download the goals

Download the goals from the following link and put it here: (PASF DIR)/multiworld/envs/mujoco.

$ ls (PASF DIR)/multiworld/envs/mujoco
... goals ... 
  1. (Optional) Speed up with GPU rendering

3. (Optional) Speed-up with GPU rendering

Note: GPU rendering for mujoco-py speeds up training a lot but consumes more GPU memory at the same time.

Check this Issues:

Remember to do this stuff with the mujoco-py package inside of your pasf_env.

Running Experiments

The following command run the PASF experiments for the four tasks: Reach, Door, Push, Pickup, in the learning curve respectively.

$ source activate pasf_env
(pasf_env) $ bash (PASF DIR)/bash_scripts/pasf_reach_lc_exp.bash
(pasf_env) $ bash (PASF DIR)/bash_scripts/pasf_door_lc_exp.bash
(pasf_env) $ bash (PASF DIR)/bash_scripts/pasf_push_lc_exp.bash
(pasf_env) $ bash (PASF DIR)/bash_scripts/pasf_pickup_lc_exp.bash
  • The bash scripts only set equation, equation, and equation with the exact values we used for LC. But you can play with other hyperparameters in python scripts under (PASF DIR)/experiment.

  • Training and evaluation environments are chosen in python scripts for each task. You can find the backgrounds in (PASF DIR)/multiworld/core/background and domains in (PASF DIR)/multiworld/envs/assets/sawyer_xyz.

  • Results are recorded in progress.csv under (PASF DIR)/data/ and variant.json contains configuration for each experiment.

  • We simply set random seeds as 0, 1, 2, etc., and run experiments with 6-9 different seeds for each task.

  • Error and output logs can be found in (PASF DIR)/terminal_log.

Questions

If you have any questions, comments, or suggestions, please reach out to Beining Han ([email protected]) and Chongyi Zheng ([email protected]).

Owner
Chongyi Zheng
Chongyi Zheng
Kroomsa: A search engine for the curious

Kroomsa A search engine for the curious. It is a search algorithm designed to en

Wingify 7 Jun 20, 2022
Official code of paper "PGT: A Progressive Method for Training Models on Long Videos" on CVPR2021

PGT Code for paper PGT: A Progressive Method for Training Models on Long Videos. Install Run pip install -r requirements.txt. Run python setup.py buil

Bo Pang 27 Mar 30, 2022
Code for KHGT model, AAAI2021

KHGT Code for KHGT accepted by AAAI2021 Please unzip the data files in Datasets/ first. To run KHGT on Yelp data, use python labcode_yelp.py For Movi

32 Nov 29, 2022
PyTorch implementation of Wide Residual Networks with 1-bit weights by McDonnell (ICLR 2018)

1-bit Wide ResNet PyTorch implementation of training 1-bit Wide ResNets from this paper: Training wide residual networks for deployment using a single

Sergey Zagoruyko 122 Dec 07, 2022
ICCV2021 - A New Journey from SDRTV to HDRTV.

ICCV2021 - A New Journey from SDRTV to HDRTV.

XyChen 82 Dec 27, 2022
Simple implementation of OpenAI CLIP model in PyTorch.

It was in January of 2021 that OpenAI announced two new models: DALL-E and CLIP, both multi-modality models connecting texts and images in some way. In this article we are going to implement CLIP mod

Moein Shariatnia 226 Jan 05, 2023
[NeurIPS 2021] "Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems"

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems Introduction Multi-agent control i

VITA 6 May 05, 2022
Black-Box-Tuning - Black-Box Tuning for Language-Model-as-a-Service

Black-Box-Tuning Source code for paper "Black-Box Tuning for Language-Model-as-a-Service". Being busy recently, the code in this repo and this tutoria

Tianxiang Sun 149 Jan 04, 2023
A repository for the paper "Improved Adversarial Systems for 3D Object Generation and Reconstruction".

Improved Adversarial Systems for 3D Object Generation and Reconstruction: This is a repository for the paper "Improved Adversarial Systems for 3D Obje

Edward Smith 188 Dec 25, 2022
The authors' official PyTorch SigWGAN implementation

The authors' official PyTorch SigWGAN implementation This repository is the official implementation of [Sig-Wasserstein GANs for Time Series Generatio

9 Jun 16, 2022
This project is based on RIFE and aims to make RIFE more practical for users by adding various features and design new models

CPM 项目描述 CPM(Chinese Pretrained Models)模型是北京智源人工智能研究院和清华大学发布的中文大规模预训练模型。官方发布了三种规模的模型,参数量分别为109M、334M、2.6B,用户需申请与通过审核,方可下载。 由于原项目需要考虑大模型的训练和使用,需要安装较为复杂

hzwer 190 Jan 08, 2023
Personalized Federated Learning using Pytorch (pFedMe)

Personalized Federated Learning with Moreau Envelopes (NeurIPS 2020) This repository implements all experiments in the paper Personalized Federated Le

Charlie Dinh 226 Dec 30, 2022
[CVPR 2022] TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing (CVPR 2022) This repository provides the official PyTorch impleme

Billy XU 128 Jan 03, 2023
Natural Intelligence is still a pretty good idea.

Human Learn Machine Learning models should play by the rules, literally. Project Goal Back in the old days, it was common to write rule-based systems.

vincent d warmerdam 641 Dec 26, 2022
The offcial repository for 'CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos', SIGIR2022

CharacterBERT-DR The offcial repository for CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos, Sh

ielab 11 Nov 15, 2022
Pytorch implementation of ProjectedGAN

ProjectedGAN-pytorch Pytorch implementation of ProjectedGAN (https://arxiv.org/abs/2111.01007) Note: this repository is still under developement. @InP

Dominic Rampas 17 Dec 14, 2022
FreeSOLO for unsupervised instance segmentation, CVPR 2022

FreeSOLO: Learning to Segment Objects without Annotations This project hosts the code for implementing the FreeSOLO algorithm for unsupervised instanc

NVIDIA Research Projects 253 Jan 02, 2023
Official source code of paper 'IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo'

IterMVS official source code of paper 'IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo' Introduction IterMVS is a novel lear

Fangjinhua Wang 127 Jan 04, 2023
A graph adversarial learning toolbox based on PyTorch and DGL.

GraphWar: Arms Race in Graph Adversarial Learning NOTE: GraphWar is still in the early stages and the API will likely continue to change. 🚀 Installat

Jintang Li 54 Jan 05, 2023
The LaTeX and Python code for generating the paper, experiments' results and visualizations reported in each paper is available (whenever possible) in the paper's directory

This repository contains the software implementation of most algorithms used or developed in my research. The LaTeX and Python code for generating the

João Fonseca 3 Jan 03, 2023